Add callbacks (#7315)

* Add `on_train_start()` callback

* Update

* Update

train.py

@@ -66,6 +66,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
     save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze = \
         Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \
         opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze
+    callbacks.run('on_pretrain_routine_start')
 
     # Directories
     w = save_dir / 'weights'  # weights dir
@@ -291,11 +292,13 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
     scaler = amp.GradScaler(enabled=cuda)
     stopper = EarlyStopping(patience=opt.patience)
     compute_loss = ComputeLoss(model)  # init loss class
+    callbacks.run('on_train_start')
     LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n'
                 f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n'
                 f"Logging results to {colorstr('bold', save_dir)}\n"
                 f'Starting training for {epochs} epochs...')
     for epoch in range(start_epoch, epochs):  # epoch ------------------------------------------------------------------
+        callbacks.run('on_train_epoch_start')
         model.train()
 
         # Update image weights (optional, single-GPU only)
@@ -317,6 +320,7 @@ def train(hyp, opt, device, callbacks):  # hyp is path/to/hyp.yaml or hyp dictio
             pbar = tqdm(pbar, total=nb, bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')  # progress bar
         optimizer.zero_grad()
         for i, (imgs, targets, paths, _) in pbar:  # batch -------------------------------------------------------------
+            callbacks.run('on_train_batch_start')
             ni = i + nb * epoch  # number integrated batches (since train start)
             imgs = imgs.to(device, non_blocking=True).float() / 255  # uint8 to float32, 0-255 to 0.0-1.0